Transmission tower key component positioning method

Abstract

The invention relates to a transmission tower key component positioning method comprising the following steps: collecting point cloud data of a transmission tower, preprocessing the point cloud data, and modeling the transmission tower based on the preprocessed point cloud data; constructing a power transmission tower modeling and repairing model, and repairing the power transmission tower modeling through the power transmission tower modeling and repairing model to obtain a repaired power transmission tower modeling; and carrying out component segmentation on the repaired transmission tower model, and screening key components from segmented components through key component evaluation indexes.

Description

Technical Field

[0001] The invention relates to a method for positioning key components of a power transmission tower, and belongs to the technical field of power inspection. Background Art

[0002] In the maintenance and management of power transmission lines, pole towers, as important structures supporting power lines, play a vital role. The various components of the towers (such as tower body, crossarms, insulators, etc.) are subject to huge mechanical stress and environmental impacts. Regular inspection and maintenance of these components is the key to ensuring the safe operation of transmission lines.

[0003] The structure of a pole tower is usually complex, consisting of multiple components and connection points. The design and layout of different components are affected by the combined effects of structural mechanics, material mechanics and environmental factors. The components of a pole tower include the main tower body, horizontal arms, cable stays, insulators, grounding devices, etc., which usually have a high degree of geometric complexity and internal hollow structures. Correctly locating and identifying these components is crucial for subsequent maintenance and repair work.

[0004] Traditional methods of locating tower components rely on manual inspection and traditional measurement tools, such as total stations and theodolites. These methods are usually time-consuming, inefficient, and limited by environmental conditions (such as weather, light, etc.) and manual measurement errors. Manual inspections are difficult to fully and accurately obtain detailed information about towers, especially for components at high altitudes or with complex structures.

[0005] The invention patent with the publication number "CN116756817A" proposes a method for quickly constructing a three-dimensional model of a tower based on the key parameters of the tower, including the following steps: S1. Make the tower head, cross arm, tower body and tower leg templates of the tower according to the existing tower type library; S2. Combine and classify the above templates according to voltage, circuit and type and define them; S3. Select the only combination of tower templates according to the call height, and adjust the model height parameterically; S4. Display the combined and parameterized tower model, and output the tower GIM. This method solves the technical problems of low efficiency, long cycle, difficult quality assurance and easy impact on the progress of the entire engineering design process in the existing tower design process. It adopts the method of optimal combination plus parameterization, and only requires the key parameters of the tower to quickly construct a three-dimensional model of the tower. It can not only improve the efficiency of structural design, but also make the design inherited and easy for engineering designers to learn and master;

[0006] However, the above method only proposes a method for constructing a three-dimensional model of a tower, but does not propose a method for locating key parts. Summary of the invention

[0007] In order to solve the above problems existing in the prior art, the present invention proposes a method for positioning key components of a transmission tower.

[0008] The technical solution of the present invention is as follows:

[0009] A method for locating key components of a transmission tower comprises the following steps:

[0010] Collect point cloud data of transmission towers, pre-process the point cloud data, and then model the transmission towers based on the pre-processed point cloud data;

[0011] Constructing a transmission tower modeling and repairing model, repairing the transmission tower modeling through the transmission tower modeling and repairing model, and obtaining a repaired transmission tower modeling;

[0012] The repaired transmission tower is modeled and segmented into components, and key components are selected from the segmented components using the key component evaluation index.

[0013] As a preferred embodiment of the present invention, the step of preprocessing the point cloud data specifically includes:

[0014] The average distance from each point in the point cloud to its k neighboring points is calculated by a statistical filter, as shown in the following formula:

[0015]

[0016] Among them: i represents the i-th point in the point cloud; o j Indicates point o i The jth neighboring point of ;

[0017] Based on the average distance from each point to its k neighboring points, the following formula is used to determine whether the point is a noise point, and all noise points are removed;

[0018] d mean (o i )>μ+α·σ

[0019] Where: μ is the global average distance; σ is the standard deviation; α is the denoising coefficient.

[0020] As a preferred embodiment of the present invention, the training steps of the transmission tower modeling and repairing model are:

[0021] The incomplete 3D model of the transmission tower and its corresponding complete 3D model of the transmission tower are input into the transmission tower modeling and repairing model for training. The transmission tower modeling and repairing model extracts the geometric features of the incomplete 3D model of the transmission tower. The specific steps are as follows:

[0022] The vertex set V = {v1,v2,…,v i}, for each vertex, construct its neighborhood vertex set N i , and extract the geometric features of the vertex based on the neighborhood vertices;

[0023] The missing area of ​​the three-dimensional model of the transmission tower is determined by the geometric features of all vertices of the incomplete three-dimensional model of the transmission tower, and the missing area is repaired according to the geometric features of the vertices within a fixed range around the missing area.

[0024] The repaired 3D model of the transmission tower is compared with its corresponding complete 3D model of the tower, and the model loss is determined by the loss function. When the model loss reaches the threshold, the model training is completed.

[0025] As a preferred embodiment of the present invention, for the hollow area in the three-dimensional model of the transmission tower, the neighborhood void fraction is defined for judgment, as shown in the following formula:

[0026]

[0027] Where: G i Indicates v i When the neighborhood porosity is greater than the threshold, the vertex is judged to belong to the hollow area, and the hollow area vertex set V is constructed. hole ;

[0028] When the three-dimensional model of the transmission tower is repaired, the repair function L of the hollow area is used. hole The specific interval between the constrained hollow areas is as follows:

[0029]

[0030] Where: dtarget represents the target interval distance of the hollow area.

[0031] As a preferred embodiment of the present invention, the component segmentation of the repaired transmission tower model is achieved by a component segmentation model, and the training steps of the component segmentation model are:

[0032] A component segmentation model is constructed based on a machine learning algorithm. The transmission tower modeling and its segmented component modeling are used as training sets. The training sets are input into the component segmentation model for training. The component segmentation model learns the geometric features of the segmented component modeling, segments the transmission tower modeling, and calculates the accuracy of each segmentation result. When the accuracy of the segmentation result reaches a threshold, the training is stopped to obtain a trained component segmentation model.

[0033] As a preferred embodiment of the present invention, the calculation formula of the key component evaluation index is:

[0034] KCI i =α1·S geo,i +α2·S conn,i +α3·S fune,i +α4·S sta,i

[0035] Among them: KCI i represents the key component evaluation index of the i-th component; S geo,i represents the geometric feature score of the i-th component; S conn,i represents the connectivity score of the i-th component; S fune,i represents the failure probability score of the i-th component; S sta,i represents the stability score of the i-th component; α1, α2, α3, and α4 are all weight parameters;

[0036] Set a critical component evaluation index threshold and filter components whose critical component evaluation index is greater than the threshold as critical components.

[0037] As a preferred embodiment of the present invention, the key component evaluation index calculation formula is:

[0038]

[0039] Where: C mean,i represents the curvature of the i-th component; C represents the curvature set of all components; A i represents the surface area of ​​the i-th component; A represents the surface area set of all components; α curv , α area , τ are weight parameters respectively; S f represents the shape factor;

[0040] The calculation formula of the connectivity score is:

[0041] S conn,i =(B,R i )+tanh(β t ·T conn,i )

[0042] Where: B is the adjacency matrix; R i is the connection vector of the i-th component; T conn,i is the connection type factor of the i-th component; β t is the weight parameter;

[0043] The calculation formula for the failure probability score is:

[0044]

[0045] Where: H i represents the historical maintenance record of the i-th component; represents an empirical constant;

[0046] The calculation formula of the stability score is:

[0047]

[0048] Where: t represents the time threshold; σ i Indicates that component i is subjected to stress; E i represents the stiffness of component i; e -λt represents the decay index; T evn Represents environmental factors.

[0049] On the other hand, the present invention also provides a transmission tower key component positioning system, including a transmission tower modeling module, a transmission tower modeling repair module and a key component positioning module;

[0050] The transmission tower modeling module is used to collect point cloud data of the transmission tower, pre-process the point cloud data, and then model the transmission tower based on the pre-processed point cloud data;

[0051] The transmission tower modeling and repairing module is used to construct a transmission tower modeling and repairing model, and repair the transmission tower modeling through the transmission tower modeling and repairing model to obtain a repaired transmission tower modeling;

[0052] The key component positioning module is used to model the repaired transmission tower and segment the components, and select key components from the segmented components according to the key component evaluation index.

[0053] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0054] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0055] The present invention has the following beneficial effects:

[0056] 1. The present invention realizes high-precision modeling and automated repair of transmission tower components by integrating point cloud data, image processing and machine learning technologies. At the same time, the key components of the transmission tower are located through the key component evaluation index, which reduces manual operation and cost and enhances maintenance and management capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0060] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0061] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0062] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0063] Embodiment 1:

[0064] See also Figure 1 , a method for locating key components of a transmission tower, comprising the following steps:

[0065] Collect point cloud data of transmission towers, pre-process the point cloud data, and then model the transmission towers based on the pre-processed point cloud data;

[0066] Constructing a transmission tower modeling and repairing model, repairing the transmission tower modeling through the transmission tower modeling and repairing model, and obtaining a repaired transmission tower modeling;

[0067] The repaired transmission tower is modeled and segmented into components, and key components are selected from the segmented components using the key component evaluation index.

[0068] As a preferred implementation of this embodiment, the step of preprocessing the point cloud data specifically includes:

[0069] The average distance from each point in the point cloud to its k neighboring points is calculated by a statistical filter, as shown in the following formula:

[0070]

[0071] Among them: i represents the i-th point in the point cloud; o j Indicates point o i The jth neighboring point of ;

[0072] Based on the average distance from each point to its k neighboring points, the following formula is used to determine whether the point is a noise point, and all noise points are removed;

[0073] d mean (o i )>μ+α·σ

[0074] Where: μ is the global average distance; σ is the standard deviation; α is the denoising coefficient, which is set to 1.5.

[0075] As a preferred implementation of this embodiment, the training steps of the transmission tower modeling and repairing model are:

[0076] The incomplete 3D model of the transmission tower and its corresponding complete 3D model of the transmission tower are input into the transmission tower modeling and repairing model for training. The transmission tower modeling and repairing model extracts the geometric features of the incomplete 3D model of the transmission tower. The specific steps are as follows:

[0077] The vertex set V = {v1,v2,…,v i}, for each vertex, construct its neighborhood vertex set N i , and extract the geometric features of the vertex based on the neighborhood vertices;

[0078] The missing area of ​​the three-dimensional model of the transmission tower is determined by the geometric features of all vertices of the incomplete three-dimensional model of the transmission tower, and the missing area is repaired according to the geometric features of the vertices within a fixed range around the missing area.

[0079] The geometric feature of the vertex is the normal vector change. The missing area is determined based on the geometric feature of the vertex. The specific steps are:

[0080] The normal vector describes the direction of the modeled surface. When the normal surface area is relatively smooth, the change in the direction of the normal vectors of adjacent points of the vertex should be small. A sudden large change in the normal vector may mean that the surface of the area is discontinuous or missing, as shown in the following formula:

[0081]

[0082] Where: Δn(p i ) represents the vertex v i The normal vector transformation of the neighboring vertices; p i Represents vertex v i Normal vector; N pi Represents vertex vi The normal vector set of the neighboring vertices; p j Represents the neighborhood vertex v j The normal vector of the tangent plane; I represents the unit matrix, which means projecting the normal vector onto the tangent plane; w ij For p j P i The weighting coefficient of Where ε is an empirical constant;

[0083] The repaired 3D model of the transmission tower is compared with the corresponding complete 3D model of the power tower, and the model loss is determined by the loss function. When the model loss reaches the threshold, the model training is completed.

[0084] In this embodiment, the transmission tower modeling and repair model is constructed based on a convolutional neural network;

[0085] As a preferred implementation of this embodiment, for the hollow area in the three-dimensional model of the transmission tower, the neighborhood void fraction is defined for judgment, as shown in the following formula:

[0086]

[0087] Where: G i Indicates v i When the neighborhood porosity is greater than the threshold, the vertex is judged to belong to the hollow area, and the hollow area vertex set V is constructed. hole ;

[0088] When the three-dimensional model of the transmission tower is repaired, the repair function L of the hollow area is used. hole The specific interval between the constrained hollow areas is as follows:

[0089]

[0090] Where: dtarget represents the target interval distance of the hollow area.

[0091] As a preferred implementation of this embodiment, the component segmentation of the repaired transmission tower model is achieved through a component segmentation model, and the training steps of the component segmentation model are:

[0092] A component segmentation model is constructed based on a machine learning algorithm. The transmission tower model and its segmented component model are used as training sets. The training sets are input into the component segmentation model for training. The component segmentation model learns the geometric features of the segmented component model, segments the transmission tower model, and calculates the accuracy of each segmentation result. When the accuracy of the segmentation result reaches a threshold, the training is stopped to obtain a trained component segmentation model.

[0093] In this embodiment, the component segmentation model is constructed based on a convolutional neural network or a support vector machine;

[0094] The geometric feature of the component modeling is curvature, which is used to capture the curvature of the local surface and helps to identify curved components and edges;

[0095] Based on the vertex normal vector, the local curvature of the vertex is calculated as shown in the following formula:

[0096]

[0097] Where: θ represents the weight parameter that adjusts the influence of the second-order change of the normal vector; Indicates v i The second-order derivative of the normal vector represents the rate of change of the local surface shape;

[0098] When the curvature reaches a preset threshold, the vertex is considered to be a component edge vertex, and the component is segmented according to all the component edge vertices.

[0099] As a preferred implementation of this embodiment, the calculation formula of the key component evaluation index is:

[0100] KCI i =α1·S geo,i +α2·S conn,i +α3·S fune,i +α4·S sta,i

[0101] Among them: KCI i represents the key component evaluation index of the i-th component; S geo,i represents the geometric feature score of the i-th component; S conn,i represents the connectivity score of the i-th component; S fune,i represents the failure probability score of the i-th component; S sta,i represents the stability score of the i-th component; α1, α2, α3, and α4 are all weight parameters;

[0102] Set a critical component evaluation index threshold and filter components whose critical component evaluation index is greater than the threshold as critical components.

[0103] As a preferred implementation of this embodiment, the key component evaluation index calculation formula is:

[0104]

[0105] Where: C mean,i represents the curvature of the i-th component; C represents the curvature set of all components; A i represents the surface area of ​​the i-th component; A represents the surface area set of all components; αcurv , α area , τ are weight parameters respectively; S f Represents the shape factor, which is used to measure the regularity and complexity of the shape of the component, such as aspect ratio, surface area to volume ratio, etc.;

[0106] The calculation formula of the connectivity score is:

[0107] S conn,i =(B,R i )+tanh(β t ·T conn,i )

[0108] Where: B is the adjacency matrix; R i is the connection vector of the i-th component, that is, the number of connection points of the i-th component. Through matrix multiplication, it can reflect the influence of the component as the center point in the structure, forming a propagation effect; T conn,i is the connection type factor of the i-th component, reflecting the physical properties of the connection (such as rigid connection, flexible connection, bolt connection, welding, etc.). Different types of connections have different effects on the overall connection. t is the weight parameter;

[0109] The calculation formula for the failure probability score is:

[0110]

[0111] Where: H i represents the historical maintenance record of the i-th component; represents the empirical constant; the failure probability score shows the impact of environmental influences and maintenance conditions on component failure;

[0112] The calculation formula of the stability score is:

[0113]

[0114] Where: t represents the time threshold, which reflects the cumulative effect of stress over time through integral calculation, reflecting the performance of the component under long-term load; σ i It means that component i is subjected to stress. The greater the force borne by the component in the structure, the higher the score; E i represents the stiffness of component i; e -λt It represents the attenuation index, which is used to reflect the attenuation trend of material properties in long-term use. As time goes by, the stiffness of the material will gradually decay, but the impact is small at the beginning; T evn Represents the environmental factor, which is used to measure the impact of environmental factors on the stability of components (such as wind, frost, corrosion, etc.). The greater the environmental impact factor, the higher the score, indicating that the component is more susceptible to environmental impact.

[0115] Embodiment 2:

[0116] A transmission tower key component positioning system, comprising a transmission tower modeling module, a transmission tower modeling repair module and a key component positioning module;

[0117] The transmission tower modeling module is used to collect point cloud data of the transmission tower, pre-process the point cloud data, and then model the transmission tower based on the pre-processed point cloud data;

[0118] The transmission tower modeling and repairing module is used to construct a transmission tower modeling and repairing model, and repair the transmission tower modeling through the transmission tower modeling and repairing model to obtain a repaired transmission tower modeling;

[0119] The key component positioning module is used to model the repaired transmission tower and segment the components, and select key components from the segmented components according to the key component evaluation index.

[0120] This module is used to implement the method in Example 1 and will not be described in detail here.

[0121] Embodiment three:

[0122] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0123] Embodiment 4:

[0124] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0125] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0126] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0129] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for locating key components of a transmission tower, characterized in that: The following steps are involved: Collect point cloud data of transmission towers, pre-process the point cloud data, and then model the transmission towers based on the pre-processed point cloud data; Constructing a transmission tower modeling and repairing model, repairing the transmission tower modeling through the transmission tower modeling and repairing model, and obtaining a repaired transmission tower modeling; The repaired transmission tower is modeled and segmented into components, and key components are selected from the segmented components using the key component evaluation index.

2. A method for locating key components of a transmission tower according to claim 1, characterized in that: The preprocessing steps of the point cloud data specifically include: The average distance from each point in the point cloud to its k neighboring points is calculated by a statistical filter, as shown in the following formula: Among them: i represents the i-th point in the point cloud; o j Indicates point o i The jth neighboring point of ; Based on the average distance from each point to its k neighboring points, the following formula is used to determine whether the point is a noise point, and all noise points are removed; d mean (the i )>μ+a·s Where: μ is the global average distance; σ is the standard deviation; α is the denoising coefficient.

3. A method for locating key components of a transmission tower according to claim 1, characterized in that: The training steps of the transmission tower modeling and repair model are as follows: The incomplete 3D model of the transmission tower and its corresponding complete 3D model of the transmission tower are input into the transmission tower modeling and repairing model for training. The transmission tower modeling and repairing model extracts the geometric features of the incomplete 3D model of the transmission tower. The specific steps are as follows: The vertex set V = {v1,v2,…,v i }, for each vertex, construct its neighborhood vertex set N i , and extract the geometric features of the vertex based on the neighborhood vertices; The missing area of ​​the three-dimensional model of the transmission tower is determined by the geometric features of all vertices of the incomplete three-dimensional model of the transmission tower, and the missing area is repaired according to the geometric features of the vertices within a fixed range around the missing area. The repaired 3D model of the transmission tower is compared with its corresponding complete 3D model of the tower, and the model loss is determined by the loss function. When the model loss reaches the threshold, the model training is completed.

4. A method for locating key components of a transmission tower according to claim 3, characterized in that: For the hollow area in the three-dimensional model of the transmission tower, the neighborhood void fraction is defined for judgment, as shown in the following formula: Where: G i Indicates v i When the neighborhood porosity is greater than the threshold, the vertex is judged to belong to the hollow area, and the hollow area vertex set V is constructed. hole ; When the three-dimensional model of the transmission tower is repaired, the repair function L of the hollow area is used. hole The specific interval between the constrained hollow areas is as follows: Where: dtarget represents the target interval distance of the hollow area.

5. A method for locating key components of a transmission tower according to claim 1, characterized in that: The component segmentation of the repaired transmission tower model is achieved by a component segmentation model, and the training steps of the component segmentation model are: A component segmentation model is constructed based on a machine learning algorithm. The transmission tower modeling and its segmented component modeling are used as training sets. The training sets are input into the component segmentation model for training. The component segmentation model learns the geometric features of the segmented component modeling, segments the transmission tower modeling, and calculates the accuracy of each segmentation result. When the accuracy of the segmentation result reaches a threshold, the training is stopped to obtain a trained component segmentation model.

6. A method for locating key components of a transmission tower according to claim 1, characterized in that: The calculation formula of the key component evaluation index is: KCI i =α1·S geo,i +α2·S conn,i +α3·S fune,i +α4·S sta,i Among them: KCI i represents the key component evaluation index of the i-th component; S geo,i represents the geometric feature score of the i-th component; S conn,i represents the connectivity score of the i-th component; S fune,i represents the failure probability score of the i-th component; S sta,i represents the stability score of the i-th component; α1, α2, α3, and α4 are all weight parameters; Set a critical component evaluation index threshold and filter components whose critical component evaluation index is greater than the threshold as critical components.

7. A method for locating key components of a transmission tower according to claim 6, characterized in that: The calculation formula of the key component evaluation index is: Where: C mean,i represents the curvature of the i-th component; C represents the curvature set of all components; A i represents the surface area of ​​the i-th component; A represents the surface area set of all components; α curv , α area , τ are weight parameters respectively; S f represents the shape factor; The calculation formula of the connectivity score is: S conn,i =(B,R i )+tanh(β t ·T conn,i ) Where: B is the adjacency matrix; R i is the connection vector of the i-th component; T conn,i is the connection type factor of the i-th component; β t is the weight parameter; The calculation formula for the failure probability score is: Where: H i represents the historical maintenance record of the i-th component; represents the empirical constant; The calculation formula of the stability score is: Where: t represents the time threshold; σ i Indicates that component i is subjected to stress; E i represents the stiffness of component i; e -λt represents the decay index; T evn Represents environmental factors.

8. A transmission tower key component positioning system, characterized in that: It includes transmission tower modeling module, transmission tower modeling repair module and key component positioning module; The transmission tower modeling module is used to collect point cloud data of the transmission tower, pre-process the point cloud data, and then model the transmission tower based on the pre-processed point cloud data; The transmission tower modeling and repairing module is used to construct a transmission tower modeling and repairing model, and repair the transmission tower modeling through the transmission tower modeling and repairing model to obtain a repaired transmission tower modeling; The key component positioning module is used to model the repaired transmission tower and segment the components, and select key components from the segmented components according to the key component evaluation index.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images